Shallow Convolutional Neural Network for COVID-19 Outbreak Screening
using Chest X-rays
Abstract
Among radiological imaging data, chest X-rays are of great use in
observing COVID-19 mani- festations. For mass screening, using chest
X-rays, a computationally efficient AI-driven tool is the must to detect
COVID-19 positive cases from non-COVID ones. For this purpose, we
proposed a light-weight Convolutional Neural Network (CNN)-tailored
shallow architecture that can automatically detect COVID-19 positive
cases using chest X-rays, with no false positive. The shallow
CNN-tailored architecture was designed with fewer parameters as compared
to other deep learning models, which was validated using 130 COVID-19
positive chest X-rays. In this study, in addition to COVID-19 positive
cases, another set of non-COVID-19 cases (exactly similar to the size of
COVID-19 set) was taken into account, where MERS, SARS, Pneumonia, and
healthy chest X-rays were used. In experimental tests, to avoid possible
bias, 5-fold cross validation was followed. Using 260 chest X-rays, the
proposed model achieved an accuracy of an accuracy of 96.92%,
sensitivity of 0.942, where AUC was 0.9869. Further, the reported false
positive rate was 0 for 130 COVID-19 positive cases. This stated that
proposed tool could possibly be used for mass screening. Note to be
confused, it does not include any clinical implications. Using the exact
same set of chest X-rays collection, the current results were better
than other deep learning models and state-of-the-art works.